← Back to all news
arXiv AI By Basel Shbita, Michael Hind, Chad DeLuca, Nathan Fulton, Shubhi Asthana, Farhan Ahmed, Anisa Halimi, Yada Zhu, Mauro Martino, David Cox, Dan Gutfreund

Post-Training Large Language Models with LLMON

Read the original on arXiv AI →

Large Language Models (LLMs) treat all context tokens uniformly, which creates prompt injection vulnerabilities and unreliable instruction execution. The paper introduces LLMON (LLM Object Notation), a post‑training framework that separates executable instructions from passive data and requires explicit identifier‑based execution. Using a 4.6 B‑token structured corpus and post‑training on Granite‑4.1 models, LLMON reduces indirect prompt‑injection success rates from 53–100 % to 0.02–5.6 % while maintaining general capabilities, and provides attention‑based interpretability metrics to diagnose failure modes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computation and Language
Aug 27

Synthesizing Instruction-Tuning Datasets with Contrastive Decoding

The paper introduces CoDIT, a contrastive decoding technique that separates instruction-following behavior from pre-trained world knowledge in large language models. By generating responses that emphasize post-training instruction capabilities while suppressing shared pre-trained knowledge, CoDIT creates instruction-tuning datasets that lead to consistently better model performance than directly generated responses or existing public datasets. The authors also provide theoretical and empirical evidence that CoDIT effectively distills instruction-tuning knowledge from model parameters into text, facilitating cross-architecture transfer.

By Tatsuya Ichinose, Youmi Ma, Masanari Oi, Ryuto Koike, Naoaki Okazaki
llmsfine-tuningbenchmarks
More like this →